Enhanced goal-based audience selection

Abstract

Devices, systems, and methods are provided for goal-based audience selection. A method for generating an audience using machine learning may include receiving a request to generate an audience for an advertisement campaign, the request including an objective associated with presentation of the advertisement campaign. The method may include determining first user actions based on the objective, and identifying first users of a system who performed the first user actions using the system. The method may include determining second user actions performed by the first users prior to performing the first user actions, and identifying second users of the system who performed the second user actions and failed to perform the first user actions. The method may include generating a target audience to which to present the advertisement campaign, and causing presentation of the advertisement campaign to the target audience.

What is claimed is: 
     
       1. A method for generating an audience to which to present an advertisement campaign based on an objective of the advertisement campaign, the method comprising:
 receiving, by a device, a request to generate a target audience for an advertisement campaign, wherein the request comprises an objective associated with presentation of the advertisement campaign, and wherein the target audience and audience criteria defining the target audience are absent from the request; 
 generating, by the device, using a machine learning model configured to generate, responsive to the request from which the target audience and the audience criteria defining the target audience are absent, based on the machine learning model being trained with user preference data to model a sequence of user actions of a system, predictions of which of the user actions are most likely to result in satisfaction of the objective; 
 identifying, by the device, using the machine learning model, first user actions of a system predicted by the machine learning model to result in satisfaction of the objective; 
 identifying, by the device, using the machine learning model, first users of the system who performed the first user actions; 
 determining, by the device, using the machine learning model, second user actions performed by the first users prior to performing the first user actions, the second user actions having probabilities exceeding a threshold indicating a likelihood that the second user actions will result in subsequent performance of the first user actions; 
 determining, by the device, using the machine learning model, third user actions performed by the first users prior to performing the first user actions, the third user actions having probabilities below the threshold; 
 identifying, by the device, using the machine learning model, based on the second user actions having probabilities exceeding the threshold, second users of the system who performed the second user actions and failed to perform the first user actions; 
 generating, by the device, as an output of the machine learning model, the target audience to which to present the advertisement campaign, the target audience comprising the second users and excluding the first users; 
 causing presentation, by the device, of the advertisement campaign to the target audience; 
 receiving, by the device, in response to the presentation of the advertisement campaign to the target audience, data indicative of a performance of the advertisement campaign, wherein data indicative of a performance of the advertisement campaign comprises an action of viewing at least one advertisement of the advertising campaign; and 
 updating, by the device, the machine learning model based on the action viewing the advertisement campaign, the data indicative of the performance of the advertisement campaign, the predictions of first user actions that are most likely to result in satisfaction of the objective. 
 
     
     
       2. The method of  claim 1 , wherein:
 the objective is to increase purchases of a product advertised by the advertisement campaign, 
 identifying the first users of the system comprises determining that the first users have purchased the product using the system, 
 determining the second user actions comprises determining that the first users viewed a product page describing the product prior to purchasing the product, and 
 identifying the second users of the system who performed the second user actions and failed to perform the first user actions comprises determining that the second users have viewed the product page and have failed to purchase the product. 
 
     
     
       3. The method of  claim 1 , further comprising:
 identifying third users of the system who performed the first user actions; 
 determining that a first subset of the third users performed the first user actions within a threshold amount of time; and 
 determining that a second subset of the third users failed to perform the first user actions within the threshold amount of time, 
 wherein the first users of the system comprise the first subset of the third users and exclude the second subset of the third users. 
 
     
     
       4. The method of  claim 1 , further comprising:
 determining third user actions performed by the first users prior to performing the first user actions; 
 determining a first probability that performance of the second user actions caused performance of the first user actions; 
 determining a second probability that performance of the third user actions caused performance of the first user actions; 
 determining that the first probability is greater than the second probability; and 
 determining that the second users are to be included in the target audience based on the first probability being greater than the second probability. 
 
     
     
       5. A method for generating an audience to which to present an advertisement campaign based on an objective of the advertisement campaign, the method comprising:
 receiving, by a device, a request to generate an audience for an advertisement campaign, wherein the request comprises an objective associated with presentation of the advertisement campaign, and wherein the audience and audience criteria defining the audience are absent from the request; 
 generating, by the device, using a machine learning model configured to generate, responsive to the request from which the audience and the audience criteria defining the audience are absent, based on the machine learning model being trained to model a sequence of user actions of a system, predictions of first user actions that are most likely to result in satisfaction of the objective; 
 identifying, by the device, using the machine learning model, first users of the system who performed the first user actions using the system; 
 determining, by the device, using the machine learning model, second user actions performed by the first users prior to performing the first user actions, the second user actions having probabilities exceeding a threshold indicating a likelihood that the second user actions will result in subsequent performance of the first user actions; 
 identifying, by the device, using the machine learning model, based on the second user actions having probabilities exceeding the threshold, second users of the system who performed the second user actions; 
 generating, by the device, as an output of the machine learning model, a target audience to which to present the advertisement campaign, the target audience comprising the second users; 
 causing presentation, by the device, of the advertisement campaign to the target audience; 
 receiving, by the device, in response to the presentation of the advertisement campaign to the target audience, data indicative of a performance of the advertisement campaign, wherein data indicative of a performance of the advertisement campaign comprises an action of viewing at least one advertisement of the advertising campaign; and 
 updating, by the device, the machine learning model based on the action of viewing the advertisement campaign, the data indicative of the performance of the advertisement campaign, the predictions of first user actions that are most likely to result in satisfaction of the objective. 
 
     
     
       6. The method of  claim 5 , wherein the audience criteria defining the target audience comprise demographic data. 
     
     
       7. The method of  claim 5 , further comprising:
 determining, based on the objective, third user actions different than the first user actions and the second user actions; 
 identifying third users of the system who performed the third user actions using the system; 
 determining fourth user actions performed by the third users prior to performing the third user actions; 
 identifying fourth users of the system who performed the fourth user actions and failed to perform the third user actions; 
 generating a second target audience to which to present the advertisement campaign, the second target audience comprising the fourth users; and 
 causing presentation of the advertisement campaign to the second target audience. 
 
     
     
       8. The method of  claim 5 , wherein identifying the first users comprises determining that the first users performed the first user actions within a first amount of time, the method further comprising:
 identifying third users of the system who performed the first user actions within a second amount of time using the system, the first amount of time different than the second amount of time; 
 determining third user actions performed by the third users prior to performing the first user actions; 
 identifying fourth users of the system who performed the third user actions and failed to perform the first user actions; 
 generating a second target audience to which to present the advertisement campaign, the second target audience comprising the fourth users; and 
 causing presentation of the advertisement campaign to the second target audience. 
 
     
     
       9. The method of  claim 5 , wherein:
 the objective is to increase purchases of a product advertised by the advertisement campaign, 
 identifying the first users of the system who have performed the first user actions comprises determining that the first users have purchased the product using the system, determining the second user actions comprises determining that the first users viewed a product page describing the product prior to purchasing the product, and 
 identifying the second users of the system who performed the second user actions and failed to perform the first user actions comprises determining that the second users have viewed the product page and have failed to purchase the product. 
 
     
     
       10. The method of  claim 5 , further comprising:
 identifying third users of the system who performed the first user actions; 
 determining that a first subset of the third users performed the first user actions within a threshold amount of time; and 
 determining that a second subset of the third users failed to perform the first user actions within the threshold amount of time, 
 wherein the first users of the system comprise the first subset of the third users and exclude the second subset of the third users. 
 
     
     
       11. The method of  claim 5 , further comprising:
 determining third user actions performed by the first users prior to performing the first user actions; 
 determining a first probability that performance of the second user actions caused performance of the first user actions; 
 determining a second probability that performance of the third user actions caused performance of the first user actions; 
 determining that the first probability is greater than the second probability; and 
 determining that the second users are to be included in the target audience based on the first probability being greater than the second probability. 
 
     
     
       12. The method of  claim 5 , wherein the advertisement campaign is associated with a first product, the method further comprising:
 identifying a unique identifier of the product; 
 identifying a brand associated with the product; and 
 determining a second product associated with the brand, 
 wherein determining the first user actions is based on the second product. 
 
     
     
       13. The method of  claim 5 , further comprising:
 identifying third users of the second users, wherein the third users performed the first user actions using the system; 
 generating a second target audience to which to present the advertisement campaign, the second target audience excluding the third users; and 
 causing presentation of the advertisement campaign to the second target audience. 
 
     
     
       14. The method of  claim 5 , further comprising:
 identifying third users of the second users, wherein the third users failed to perform third user actions using the system after the presentation of the advertisement campaign to the target audience; 
 generating a second target audience to which to present the advertisement campaign, the second target audience excluding the third users; and 
 causing presentation of the advertisement campaign to the second target audience. 
 
     
     
       15. The method of  claim 5 , further comprising:
 determining third user actions based on the objective; and 
 determining fourth user actions performed by the first users prior to performing the first user actions, 
 wherein identifying the first users is based on the first users having performed the third user actions using the system, and 
 wherein identifying the second users is based on the second users having failed to perform the fourth user actions. 
 
     
     
       16. The method of  claim 5 , further comprising:
 receiving, from an application programming interface (API), an indication of third users associated with at least one of a product awareness, a brand awareness, or a product purchase, 
 wherein identifying the second users is based on the indication of the third users, wherein a number of the second users is different than a number of the third users. 
 
     
     
       17. A system for generating an audience to which to present an advertisement campaign based on an objective of the advertisement campaign, the system comprising memory coupled to at least one processor, the at least one processor configured to:
 receive a request to generate an audience for an advertisement campaign, wherein the request comprises an objective associated with presentation of the advertisement campaign, and wherein the audience and audience criteria defining the audience are absent from the request; 
 generating, using a machine learning model, responsive to the request from which the audience and the audience criteria defining the audience are absent, based on the machine learning model being trained to model a sequence of user actions of a system, predictions of first user actions that are most likely to result in satisfaction of the objective; 
 identify, using the machine learning model, first users of the system who performed the first user actions using the system; 
 determine, using the machine learning model, second user actions performed by the first users prior to performing the first user actions, the second user actions having probabilities exceeding a threshold indicating a likelihood that the second user actions will result in subsequent performance of the first user actions; 
 identify, using the machine learning model, based on the second user actions having probabilities exceeding the threshold, second users of the system who performed the second user actions; 
 generate, as an output of the machine learning model, a target audience to which to present the advertisement campaign, the target audience comprising the second users; 
 cause presentation of the advertisement campaign to the target audience; 
 receive, in response to the presentation of the advertisement campaign to the target audience, data indicative of a performance of the advertisement campaign, wherein data indicative of a performance of the advertisement campaign comprises an action of viewing at least one advertisement of the advertising campaign; and 
 update the machine learning model based on the action of viewing the advertisement campaign, the data indicative of the performance of the advertisement campaign, the predictions of first user actions that are most likely to result in satisfaction of the objective. 
 
     
     
       18. The system of  claim 17 , wherein criteria defining the target audience is absent from the request. 
     
     
       19. The system of  claim 17 , wherein the at least one processor is further configured to:
 determine, based on the objective, third user actions different than the first user actions and the second user actions; 
 identify third users of the system who performed the third user actions using the system; 
 determine fourth user actions performed by the third users prior to performing the third user actions; 
 identify fourth users of the system who performed the fourth user actions and failed to perform the third user actions; 
 generate a second target audience to which to present the advertisement campaign, the second target audience comprising the fourth users; and 
 cause presentation, by the at least one processor, of the advertisement campaign to the second target audience. 
 
     
     
       20. The system of  claim 17 , wherein to identify the first users comprises to determine that the first users performed the first user actions within a first amount of time, wherein the at least one processor is further configured to:
 identify third users of the system who performed the first user actions within a second amount of time using the system, the first amount of time different than the second amount of time; 
 determine third user actions performed by the third users prior to performing the first user actions; 
 identify fourth users of the system who performed the third user actions and failed to perform the first user actions; 
 generate a second target audience to which to present the advertisement campaign, the second target audience comprising the fourth users; and 
 cause presentation, by the at least one processor, of the advertisement campaign to the second target audience.